Spatially-Adaptive Reconstruction in Computed Tomography Using Neural Networks. Boublil, D., Elad, M., Shtok, J., & Zibulevsky, M. IEEE Transactions on Medical Imaging, 34(7):1474–1485, July, 2015. Conference Name: IEEE Transactions on Medical Imagingdoi abstract bibtex We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear fusion of several image estimates, all obtained by applying a chosen reconstruction algorithm with different values of its control parameters. Usually such output images have different bias/variance trade-off. The fusion of the images is performed by feed-forward neural network trained on a set of known examples. Numerical experiments show an improvement in reconstruction quality relatively to existing direct and iterative reconstruction methods.
@article{boublil_spatially-adaptive_2015,
title = {Spatially-{Adaptive} {Reconstruction} in {Computed} {Tomography} {Using} {Neural} {Networks}},
volume = {34},
issn = {1558-254X},
doi = {10.1109/TMI.2015.2401131},
abstract = {We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear fusion of several image estimates, all obtained by applying a chosen reconstruction algorithm with different values of its control parameters. Usually such output images have different bias/variance trade-off. The fusion of the images is performed by feed-forward neural network trained on a set of known examples. Numerical experiments show an improvement in reconstruction quality relatively to existing direct and iterative reconstruction methods.},
language = {en},
number = {7},
journal = {IEEE Transactions on Medical Imaging},
author = {Boublil, David and Elad, Michael and Shtok, Joseph and Zibulevsky, Michael},
month = jul,
year = {2015},
note = {Conference Name: IEEE Transactions on Medical Imaging},
keywords = {\#Biology, \#NN, \#Representation, \#Spatial, \#Vision, /unread, Artificial neural networks, Computed Tomography, Computed tomography, Image reconstruction, Noise, Photonics, Reconstruction algorithms, Training, filtered-back-projection (FBP), low-dose reconstruction, neural networks, supervised learning, ❤️},
pages = {1474--1485},
}
Downloads: 0
{"_id":"WmS9AbGfLJ5fXR4Bt","bibbaseid":"boublil-elad-shtok-zibulevsky-spatiallyadaptivereconstructionincomputedtomographyusingneuralnetworks-2015","author_short":["Boublil, D.","Elad, M.","Shtok, J.","Zibulevsky, M."],"bibdata":{"bibtype":"article","type":"article","title":"Spatially-Adaptive Reconstruction in Computed Tomography Using Neural Networks","volume":"34","issn":"1558-254X","doi":"10.1109/TMI.2015.2401131","abstract":"We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear fusion of several image estimates, all obtained by applying a chosen reconstruction algorithm with different values of its control parameters. Usually such output images have different bias/variance trade-off. The fusion of the images is performed by feed-forward neural network trained on a set of known examples. Numerical experiments show an improvement in reconstruction quality relatively to existing direct and iterative reconstruction methods.","language":"en","number":"7","journal":"IEEE Transactions on Medical Imaging","author":[{"propositions":[],"lastnames":["Boublil"],"firstnames":["David"],"suffixes":[]},{"propositions":[],"lastnames":["Elad"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Shtok"],"firstnames":["Joseph"],"suffixes":[]},{"propositions":[],"lastnames":["Zibulevsky"],"firstnames":["Michael"],"suffixes":[]}],"month":"July","year":"2015","note":"Conference Name: IEEE Transactions on Medical Imaging","keywords":"#Biology, #NN, #Representation, #Spatial, #Vision, /unread, Artificial neural networks, Computed Tomography, Computed tomography, Image reconstruction, Noise, Photonics, Reconstruction algorithms, Training, filtered-back-projection (FBP), low-dose reconstruction, neural networks, supervised learning, ❤️","pages":"1474–1485","bibtex":"@article{boublil_spatially-adaptive_2015,\n\ttitle = {Spatially-{Adaptive} {Reconstruction} in {Computed} {Tomography} {Using} {Neural} {Networks}},\n\tvolume = {34},\n\tissn = {1558-254X},\n\tdoi = {10.1109/TMI.2015.2401131},\n\tabstract = {We propose a supervised machine learning approach for boosting existing signal and image recovery methods and demonstrate its efficacy on example of image reconstruction in computed tomography. Our technique is based on a local nonlinear fusion of several image estimates, all obtained by applying a chosen reconstruction algorithm with different values of its control parameters. Usually such output images have different bias/variance trade-off. The fusion of the images is performed by feed-forward neural network trained on a set of known examples. Numerical experiments show an improvement in reconstruction quality relatively to existing direct and iterative reconstruction methods.},\n\tlanguage = {en},\n\tnumber = {7},\n\tjournal = {IEEE Transactions on Medical Imaging},\n\tauthor = {Boublil, David and Elad, Michael and Shtok, Joseph and Zibulevsky, Michael},\n\tmonth = jul,\n\tyear = {2015},\n\tnote = {Conference Name: IEEE Transactions on Medical Imaging},\n\tkeywords = {\\#Biology, \\#NN, \\#Representation, \\#Spatial, \\#Vision, /unread, Artificial neural networks, Computed Tomography, Computed tomography, Image reconstruction, Noise, Photonics, Reconstruction algorithms, Training, filtered-back-projection (FBP), low-dose reconstruction, neural networks, supervised learning, ❤️},\n\tpages = {1474--1485},\n}\n\n\n\n","author_short":["Boublil, D.","Elad, M.","Shtok, J.","Zibulevsky, M."],"key":"boublil_spatially-adaptive_2015","id":"boublil_spatially-adaptive_2015","bibbaseid":"boublil-elad-shtok-zibulevsky-spatiallyadaptivereconstructionincomputedtomographyusingneuralnetworks-2015","role":"author","urls":{},"keyword":["#Biology","#NN","#Representation","#Spatial","#Vision","/unread","Artificial neural networks","Computed Tomography","Computed tomography","Image reconstruction","Noise","Photonics","Reconstruction algorithms","Training","filtered-back-projection (FBP)","low-dose reconstruction","neural networks","supervised learning","❤️"],"metadata":{"authorlinks":{}},"downloads":0,"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/zzhenry2012","dataSources":["nZHrFJKyxKKDaWYM8"],"keywords":["#biology","#nn","#representation","#spatial","#vision","/unread","artificial neural networks","computed tomography","computed tomography","image reconstruction","noise","photonics","reconstruction algorithms","training","filtered-back-projection (fbp)","low-dose reconstruction","neural networks","supervised learning","❤️"],"search_terms":["spatially","adaptive","reconstruction","computed","tomography","using","neural","networks","boublil","elad","shtok","zibulevsky"],"title":"Spatially-Adaptive Reconstruction in Computed Tomography Using Neural Networks","year":2015}